© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9976
    Prev
    Next
    INDEX
    Explanations

    information about people's careers, especially time spent in certain roles

    oai_token-act-pair · gemini-2.0-flash

    biographies/news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.81
    tvguidetime
    -0.78
     crdi
    -0.74
    troppo
    -0.71
     MainAxisSize
    -0.71
    ükemmel
    -0.70
     समीक्षाओं
    -0.69
     Theſe
    -0.68
     Efq
    -0.67
     servos
    -0.67
    POSITIVE LOGITS
     He
    0.61
    am
    0.51
    .
    0.49
    He
    0.48
     having
    0.47
    um
    0.47
    .-
    0.47
     Br
    0.46
    ._
    0.46
    vnd
    0.45
    Activations Density 8.010%

    No Known Activations